Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4604 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0984. Min Act: 0.0000

Data Index: 1651782 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1060170 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0965. Min Act: -0.0000

Data Index: 616671 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0946. Min Act: 0.0000

Data Index: 1209247 (The Pile)

Max Activating Token Index: 540

Text #4

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0945. Min Act: 0.0000

Data Index: 963133 (The Pile)

Max Activating Token Index: 949

Text #5

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0930. Min Act: -0.0000

Data Index: 982626 (The Pile)

Max Activating Token Index: 87

Text #6

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0919. Min Act: -0.0000

Data Index: 743721 (The Pile)

Max Activating Token Index: 953

Text #7

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1012874 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1104267 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1826196 (The Pile)

Max Activating Token Index: 107

Text #10

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1855874 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0893. Min Act: -0.0000

Data Index: 834220 (The Pile)

Max Activating Token Index: 957

Text #12

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0890. Min Act: -0.0000

Data Index: 996205 (The Pile)

Max Activating Token Index: 350

Text #13

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0886. Min Act: -0.0000

Data Index: 836612 (The Pile)

Max Activating Token Index: 21

Text #14

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0881. Min Act: -0.0000

Data Index: 330975 (The Pile)

Max Activating Token Index: 39

Text #15

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0881. Min Act: 0.0000

Data Index: 1649521 (The Pile)

Max Activating Token Index: 106

Text #16

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1477232 (The Pile)

Max Activating Token Index: 13

Text #17

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0865. Min Act: 0.0000

Data Index: 964748 (The Pile)

Max Activating Token Index: 1021

Text #18

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0866. Min Act: 0.0000

Data Index: 1734853 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0865. Min Act: -0.0000

Data Index: 832410 (The Pile)

Max Activating Token Index: 57